NORMA eResearch @NCI Library

Virtual Garment Imposition using ACGPN

More, Saylee Vijay (2020) Virtual Garment Imposition using ACGPN. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (844kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


The demand for online shopping is increasing day by day. Despite having several advantages, online shopping industry fails to enables the customers to virtually try on garment on themselves before buying it. Developing a method as such would be a more significant advantage for online shopping industry as well as the customers. The goal of this research is to check whether the Adaptive Content Generative and Preserving Network (ACGPN) model can be used to impose virtual garments on the user’s images or not? All the experiments of this research are done using the python programming language. ACGPN model is tested on three types of images depending on a different level of poses such as Easy, Medium and Hard. After the inferencing ACGPN model, the results turned out that the model works accurate on Easy pose images, good on Medium pose images and fails miserably on Hard pose images. In future, if the weights of ACGPN model is adjusted, it would yield good result on all types of pose images. This successful model then can be further converted into the Torch script and can be imported into the Android or IOS application using Pytorch Mobile.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 22 Jan 2021 15:47
Last Modified: 22 Jan 2021 15:47

Actions (login required)

View Item View Item